CN115993809A

CN115993809A - Automobile network vehicle bus diagnostics

Info

Publication number: CN115993809A
Application number: CN202211258959.6A
Authority: CN
Inventors: 海萨姆·M·卡德瑞; A·戈帕尔; D·A·奥利弗; 詹姆斯·马丁·劳利斯
Original assignee: Ford Global Technologies LLC
Current assignee: Ford Global Technologies LLC
Priority date: 2021-10-20
Filing date: 2022-10-14
Publication date: 2023-04-21
Also published as: US20230122334A1; US11810409B2; DE102022127546A1

Abstract

The present disclosure provides "automotive network vehicle bus diagnostics". Performing on-board network diagnostics is provided. A cloud system receives wiring diagnostic data from a vehicle. The wiring diagnostic data includes information regarding electrical operation of a plurality of wiring segments of the vehicle. A machine learning model of the cloud system is used to analyze the wiring diagnostic data. Responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, a response is sent from the cloud system to the vehicle, the response including one or more corrective actions to be performed by the vehicle to solve the problem.

Description

Automobile network vehicle bus diagnostics

Technical Field

Aspects of the present disclosure relate generally to built-in diagnostics for an on-board network.

Background

The vehicle components send and receive data over vehicle wiring, such as Controller Area Network (CAN) or ethernet wiring. Initially, or in other cases, over time, the vehicle wiring may become unreliable. This may affect the data transmission through the vehicle wiring. Time Domain Reflectometry (TDR) is a technique for determining characteristics of an electrical wiring by providing an electrical pulse along the wiring and observing the reflected waveform. By identifying the timing or other characteristics of the reflected waveform, the location of the problem in the wiring can be identified.

Disclosure of Invention

In one or more illustrative examples, a system for performing on-board network diagnostics is provided. The system includes one or more cloud servers. The one or more cloud servers are programmed to: receiving wiring diagnostic data from a vehicle, the wiring diagnostic data including information regarding electrical operation of a plurality of wiring segments of the vehicle; analyzing the wiring diagnostic data using a machine learning model; and responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, sending a response including one or more corrective actions to be performed by the vehicle to solve the problem.

In one or more illustrative examples, a method for performing on-board network diagnostics is provided. A cloud system receives wiring diagnostic data from a vehicle. The wiring diagnostic data includes information regarding electrical operation of a plurality of wiring segments of the vehicle. A machine learning model of the cloud system is used to analyze the wiring diagnostic data. Responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, a response is sent from the cloud system to the vehicle, the response including one or more corrective actions to be performed by the vehicle to solve the problem.

In one or more illustrative examples, a non-transitory computer-readable medium comprising instructions for performing in-vehicle network diagnostics, the instructions when executed by one or more cloud servers cause the one or more cloud servers to perform operations comprising: receiving cabling diagnostic data from a vehicle, the cabling diagnostic data including information regarding electrical operation of a plurality of cabling segments of the vehicle, the cabling diagnostic data including cable diagnostic details of the plurality of cabling segments determined using Time Domain Reflectometry (TDR) functions of the vehicle integrated into a vehicle controller and/or inline with the plurality of cabling segments, the cable diagnostic details including link quality measured using the TDR functions for each of the plurality of cabling segments and cabling length for each of the plurality of cabling segments; analyzing the wiring diagnostic data using a machine learning model; and responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, sending a response including one or more corrective actions to be performed by the vehicle to solve the problem.

Drawings

FIG. 1 illustrates an exemplary system including a central gateway configured to provide on-board network diagnostics;

FIG. 2 shows the vehicle of FIG. 1 in the context of a system for performing on-board network diagnostics;

fig. 3 shows an example of wiring diagnostic data;

fig. 4 shows an example of a part of a wiring line of a vehicle of the vehicle;

FIG. 5 illustrates an exemplary process for a vehicle to perform an on-board network diagnostic;

FIG. 6 illustrates an exemplary process of a cable monitoring system performing on-board network diagnostics;

FIG. 7 illustrates an exemplary process by which the cable monitoring system retrains a machine learning model to improve on-board network diagnostics; and is also provided with

FIG. 8 illustrates an exemplary computing device for performing on-board network diagnostics.

Detailed Description

As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention that may be embodied in various and alternative forms. The figures are not necessarily to scale; some features may be exaggerated or minimized to show details of particular components. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the present invention.

Including higher speed on-board networks (such as automotive ethernet) introduces complexity in wiring diagnostics in vehicles. The vehicle may be cabled with ethernet, such as a jacketed unshielded portion of the wires between the components. Such networks may be more prone to poor cabling problems than lower throughput networks such as Controller Area Networks (CAN).

Features can be designed into the car physical layer to make wiring diagnostics and record any identified problems such as wire breaks and link quality over time. For example, some physical bus implementations may use a built-in Time Domain Reflectometer (TDR) function to perform diagnostics on cabling. This may be used to determine signal quality status or Signal Quality Indication (SQI) for each segment of the ethernet cabling within the vehicle. The trained neural network may receive such wiring diagnostics and may be used to identify and/or predict potential wiring problems. Other aspects of the disclosure are described in detail herein.

Fig. 1 illustrates an exemplary system 100 including a central gateway 110 configured to provide in-vehicle network diagnostics. The central gateway 110 may be connected to a plurality of Electronic Control Units (ECUs) 104 via one or more vehicle buses 106. The central gateway 110 may also include one or more diagnostic ports 108. Central gateway 110 may include a processor 112, memory 114, and storage 116 for applications 118 and/or data 120. Although the exemplary system 100 is shown in FIG. 1, the exemplary components shown are not intended to be limiting. Indeed, the system 100 may have more or fewer components and additional or alternative components and/or implementations may be used.

The vehicle 102 may include various types of automobiles, cross-border utility vehicles (CUVs), sport Utility Vehicles (SUVs), trucks, recreational Vehicles (RVs), boats, aircraft, or other mobile machinery for transporting personnel or cargo. In many cases, the vehicle 102 may be powered by an internal combustion engine. As another possibility, the vehicle 102 may be a Hybrid Electric Vehicle (HEV) powered by both an internal combustion engine and one or more electric motors. In another example, the vehicle 102 may be an electric-only vehicle driven by an electric motor only.

The vehicle 102 may include a plurality of Electronic Control Units (ECUs) 104 configured to perform and manage various vehicle 102 functions under power from the vehicle battery and/or driveline. As depicted, the example vehicle ECU 104 is represented as discrete ECUs 104-a through 104-H. However, the vehicle ECU 104 may share physical hardware, firmware, and/or software such that functions from multiple ECUs 104 may be integrated into a single ECU 104 or distributed across multiple ECUs 104. The vehicle ECU 104 may include various vehicle 102 components configured to receive updates of associated software, firmware, or configuration settings.

As some non-limiting examples of the vehicle ECU 104: the Powertrain Control Module (PCM) 104-a may be configured to control engine and transmission components; an anti-lock braking system (ABS) 104-B controller configured to control the braking and traction control components; an electric power steering (EPAS) 104-C controller configured to control steering assistance and adjust traction or drift compensation functions; advanced Driver Assistance Systems (ADAS) 104-D, such as adaptive cruise control or automated braking; and a Headlamp Control Module (HCM) 104-E configured to control the lamp on/off setting. The ECU 104 may also include other powertrain 104-F or chassis 104-G components, an infotainment system 104-H configured to support voice commands and bluetooth interfaces with drivers and driver-carried devices (e.g., the SYNC system provided by ford motor company of diebert, michigan), a connectivity controller 104-I (such as a Telematics Control Unit (TCU)) configured to access networked devices external to the vehicle 102 using embedded modems, an electromechanical body controller 104-J (such as windows or lock actuators), and a trailer controller 104-K component (such as light control and sensor data to support a connected trailer).

The vehicle bus 106 may include various communication methods available between the vehicle ECUs 104. The vehicle bus 106 may also support communication between the central gateway 110 and the vehicle ECU 104. As some non-limiting examples, the vehicle bus 106 may be a vehicle Controller Area Network (CAN), an ethernet network, or a Media Oriented System Transport (MOST) network. The one or more CAN networks may be of various types including, but not limited to, high speed CAN (HS-CAN) with data capacity up to 500kbps, medium speed CAN (MS-CAN) with data capacity up to 125kbps, and/or CAN flexible data rate (FD-CAN) with data capacity up to 2000kbps or higher. It should be noted that the bus topology shown is merely an example, and that other numbers and arrangements of vehicle buses 106 may be used. These vehicle buses 106 may be implemented as a series of wire segments. For example, the vehicle bus 106 may include a plurality of wire segments from the central gateway 110 to the end locations.

The vehicle 102 may also include a diagnostic port 108 that may be used by external devices to monitor the status of the vehicle 102. In one example, diagnostic port 108 may be an on-board diagnostic (OBD) port connected to vehicle bus 106. The user may connect a dongle, code reader or other scanning device to diagnostic port 108 and may use the connection provided by diagnostic port 108 to gain access to messages passing through vehicle bus 106. Once connected, the user may utilize the connected scanning device to capture diagnostic codes, monitor vehicle health, or in some cases adjust vehicle settings. Similar to the speed of HS-CAN, the CAN diagnostic port 108 may support data capacities of up to 500 kbps. In another example, diagnostic port 108 may be an internet protocol diagnostic (DoIP) port 124 and may provide access to messages across vehicle bus 106 via ethernet rather than via OBD standards. The DoIP port 124 may support higher data rates than CAN because ethernet using TCP/IP 64 byte payloads may support data rates of about 45Mbps, while 1460 byte payloads may support data rates of about 95 Mbps.

The central gateway 110 may be configured to provide an electrical interface between the vehicle buses 106 for communication within the vehicle 102. In one example, the central gateway 110 may be configured to translate signals and commands between the CAN and/or the on-board ethernet vehicle bus 106 connected to the central gateway 110. For example, the central gateway 110 may support connections with up to ten CAN vehicle buses 106 and up to seven ethernet vehicle buses 106. By supporting ethernet in addition to CAN, the central gateway 110 may be able to provide support for higher speed on-board network communications while still performing existing or legacy gateway functions within the vehicle 102.

As a specific non-limiting example, the central gateway 110 may be connected to the drivetrain 104-F components through the HS-CAN vehicle bus 106; is connected to the chassis component 104-G, the safety system and the instrument cluster via a second HS-CAN vehicle bus 106; is connected to the infotainment system 104-H via a third HS-CAN vehicle bus 106; connected to connectivity 104-I and ethernet safe backup system via fourth HS-CAN vehicle bus 106; is connected to the electromechanical body controller 104-J through a first MS-CAN bus; a node connected to the trailer controller 104-K via a second MS-CAN vehicle bus 106 and/or easily accessible from outside the vehicle 102; connected to the diagnostic port 108 through first and second diagnostic data vehicle bus 106 connections; connected to the PCM 104-A, ABS 104-B, EPAS 104-C and other controllers via a first FD-CAN vehicle bus 106; and is connected to the ADAS 104-D, HCM 104-E and other controllers via a second FD-CAN vehicle bus 106. For example, infotainment 104-H, connectivity 104-I, instrument cluster 104-L, heads-up display 104-M, and ADAS 104-D are each connected to central gateway 110 via a separate 2-wire 100 Mmsp Ethernet vehicle bus 106. In yet another example, the heads-up display 104-M may be integrated with the instrument cluster 104-L.

The central gateway 110 may also be configured to provide computing functionality that supports domain CAN messaging for the vehicle 102. For example, central gateway 110 may include one or more processors 112, the one or more processors 112 configured to execute instructions, commands, and other routines supporting the processes described herein. In one example, central gateway 110 may be configured to execute instructions of application program 118 loaded from storage medium 116 of central gateway 110 to memory 114 of central gateway 110. The application program 118 may include software code programmed to support the operation of the central gateway 110 as discussed in detail herein. For example, the application 118 may include software code for facilitating collection of data 120 from the vehicle 102, sending the data 120, and receiving commands from a remote source for execution. Computer-readable media 116 (also referred to as processor-readable media or storage) includes any non-transitory medium (e.g., tangible media) that participates in providing instructions or other data that may be read by processor 112 of central gateway 110. Computer-executable instructions may be compiled or interpreted according to computer programs created using a variety of programming languages and/or techniques, including, but not limited to, the following alone or in combination: java, C, C++, C#, objective C, fortran, pascal, java Script, python, perl, and PL/SQL. As a specific example, central gateway 110 may be equipped with at least 128 megabytes of RAM, and 2 to 4 cores of processor 112 for processing power to accomplish various computing tasks.

Fig. 2 shows the vehicle 102 of fig. 1 in the context of a system 200 for performing on-board network diagnostics. As described above, the vehicle 102 may include a connectivity controller 104-I, such as a TCU, to communicate with the cloud server 204 through the communication network 202. The cloud server 204 is configured to host a cable monitoring data store 206 that maintains the machine learning model 210 and training data 212 and a cable monitoring service 214 that is configured to receive wiring diagnostic data 218 from the vehicle 102 and to utilize the machine learning model 210 to provide corrective actions to the vehicle 102 based on analysis of the wiring diagnostic data 218 by the machine learning model 210. It should be noted that system 200 is an example and that system 200 with more, fewer, or different elements may be used.

The communication network 202 may provide communication services, such as packet-switched network services (e.g., internet access, voice over internet protocol (VoIP) communication services), to devices connected to the external communication network 202. An example of the external communication network 202 is a cellular telephone network. For example, the connectivity controller 104-I may access the cellular network via a connection with one or more cellular towers. To facilitate communications over the communication network 202, the connectivity controller 104-I may be associated with a unique device identifier (e.g., a Mobile Device Number (MDN), an Internet Protocol (IP) address, etc.) to identify communications of the connectivity controller 104-I over the communication network 202 as being associated with the vehicle 102.

Cloud server 204 may include various types of computing devices, such as a computer workstation, a server, a desktop computer, a virtual server instance executed by a mainframe computer server, or some other computing system and/or apparatus. A computing device, such as cloud server 204, typically includes memory on which computer-executable instructions may be stored, wherein the instructions are executable by one or more processors of the computing device. Such instructions and other data may be stored using a variety of computer-readable media. Computer-readable media (also referred to as processor-readable media or storage devices) include any non-transitory (e.g., tangible) media that participates in providing data (e.g., instructions) that may be read by a computer (e.g., by a processor of cloud server 204). In general, a processor receives instructions, e.g., from a memory via a computer-readable storage medium or the like, and executes the instructions, thereby performing one or more processes, including one or more of the processes described herein. Computer-executable instructions may be compiled or interpreted according to a computer program created using a variety of programming languages and/or techniques, including, but not limited to, the following singly or in combination: java, C, c++, c#, fortran, pascal, visual Basic, javaScript, perl, etc.

The cable monitoring data storage area 206 may be one such application included on the storage device of the cloud server 204. The cable monitoring data store 206 may include instructions that, when loaded into memory and executed by the cloud server 204, cause the cloud server 204 to perform database functions including storage, updating, and retrieval of relationship information. The database or data repository, such as cable monitoring data store 206, may include various mechanisms for storing, accessing, and retrieving various data, such as cable monitoring data store 206, including a hierarchical database, a set of files in a file system, a proprietary format application database, a relational database management system (RDBMS), and the like. For example, in addition to using a language for creating, storing, editing, and executing stored programs, an RDBMS may also use a Structured Query Language (SQL). In one example, data such as wiring diagnostic data 208, machine learning model 210, training data 212, and corrective action 216 may be stored.

The wiring diagnostics data 208 may include information sent from the vehicle 102 to the cloud server 204 over the communication network 202 for performing on-board network diagnostics in execution. Fig. 3 shows an example 300 of wiring diagnostic data 208. As shown in FIG. 3 and with continued reference to FIG. 2, in one example, the wiring diagnostic data 208 may include an identifier 302 (such as VIN) of the vehicle 102, cable diagnostic details 304, data transmission diagnostic details 306, and/or environmental vehicle sensor readings 308.

The cable diagnostic details 304 of the wiring diagnostic data 208 may include information regarding the electrical operation of one or more wire segments of the vehicle bus 106 of the vehicle 102. For example, some physical bus embodiments of the vehicle 102 may use a built-in Time Domain Reflectometer (TDR) function to perform diagnostics on the vehicle cabling. Such functionality may be built into one or more of the ECUs 104 of the vehicle 102. In other examples, such functionality may be inline along the vehicle cabling, such as at various nodes along the wiring lines. In the case of a disconnection or intermittent connection, the TDR information may provide an approximate length along a given wiring line where an open or short circuit exists.

Fig. 4 shows an example 400 of a portion of a wiring line of the vehicle 106 of the vehicle 102. As shown in fig. 4, the line includes three parts: a door mirror wire harness connected to a door wire harness, which in turn is connected to a body wire harness. The TDR function for monitoring the three wire segments may be included in various components of the wire line. For example, the TDR function may be included in a sensor on the door mirror harness to allow measurement from a sensor endpoint of the wiring line, inline along the wiring line to make measurements between nodes along the wiring line, and/or within the ECU 104 to which the wiring line is connected to allow measurement from the ECU 104 endpoint.

In one example, the cable diagnostic details 304 may include a table including measured link quality (e.g., using TDR functionality) and cabling length for each of the segments of the vehicle 102. For example, for the illustrated portion of the wiring line, this may include an indication of a five meter length and measured link quality of the door mirror wire harness segment, a three meter length and measured link quality of the door wire harness segment, and a four meter length and measured link quality of the connected body wire harness segment.

Referring back to fig. 3, the data transmission diagnostic details 306 of the wiring diagnostic data 208 may include information about the data transmission and the vehicle bus 106, such as channel quality (e.g., bit Error Rate (BER), signal-to-noise ratio (SNR), connection time, etc.) for each of the plurality of segments of the vehicle bus 106. This additional information may provide data to help identify the root cause of the sporadic problem and determine overall network health over time.

The surrounding vehicle sensor readings 308 of the wiring diagnostic data 208 may include information from other sensors of the vehicle 102. This may include, for example, temperature or other weather information; speed, acceleration, or other information about movement of the vehicle 102; date, time of day, etc. Such factors may also be used to help identify conditions in which intermittent problems occur.

Referring back to fig. 2, a machine learning model 210 (such as a trained neural network) may be used to perform detection of cabling problems based on cabling diagnostic data 218 received from the vehicle 102. In general, the machine learning model 210 may receive the wiring diagnostic data 218 as input and may use the data to output whether any problems with the vehicle 102 are identified. For example, the machine learning model 210 may utilize the wiring diagnostics data 218 to determine link quality and/or identify any outlier data points based on collected statistics of other vehicles 102.

The machine learning model 210 may be trained using the training data 212. The training data 212 may include wiring diagnostic data 208 labeled as indicating the link quality of the training data 212. During the training phase, this data may be used to allow adjustable parameters (such as weights and biases) in the machine learning model 210 to be adjusted to allow the machine learning model 210 to provide accurate output.

The cable monitoring service 214 may be an application or library included on the storage of the cloud server 204 or otherwise accessible by the cloud server. When accessed, the cable monitoring service 214 may be configured to request or otherwise receive wiring diagnostic data 218 from the vehicle 102. The cable monitoring service 214 may apply the received wiring diagnostic data 218 to the machine learning model 210 to determine whether the wiring diagnostic data 218 indicates a current or future possible wiring problem for the vehicle 102.

In response to the problem determined by the cable monitoring service 214, the cable monitoring service 214 may send one or more corrective actions 216 to the vehicle 102. As some examples, corrective action 216 may include an indication that vehicle 102 is informed that service is sought, a new routing of vehicle 102 data along more reliable wire segments within vehicle 102 to avoid segments with problems, and/or an update to the configuration of vehicle 102 to reduce data speed or reduce update intervals to otherwise adjust data traffic to alleviate problems of segments with problems.

The cable monitoring service 214 may also be configured to incorporate cabling diagnostic data 218 into the training data 212 to allow for retraining and improvement of the machine learning model 210. By having additional training data 212 from the active vehicle 102, the machine learning model 210 may be retrained to improve its performance over time.

For example, in response to determining a problem with the vehicle 102, the cable monitoring service 214 may extract the earlier wiring diagnostic data 218 from the vehicle 102 before the problem is detected. By analyzing the characteristics of the vehicle before the problem occurs, the cable monitoring service 214 may be able to provide predictions regarding expected maintenance problems or end-of-life for various wiring components. These predictions may be used to alert before a problem occurs and/or identify where changes are made to the design or assembly of the vehicle 102 to improve the life of the vehicle 102 components.

In some examples, the vehicle 102 may maintain data that senses test conditions 220 that define when the vehicle 102 should send cabling diagnostic data 208 to the cable monitoring system 214 for testing. For example, the test conditions 220 may instruct the vehicle 102 to transmit the wiring diagnostic data 208 in response to the vehicle 102 being in a factory mode (e.g., being built). As one possibility, when the vehicle 102 is assembled and reaches various stations, the vehicle 102 may provide its wiring diagnostic data 208 to the cable monitoring system 214 for testing. This may allow for diagnosing wiring problems when building the vehicle 102 before the final assembly is completed. By doing so, the problem can be more easily corrected before the vehicle 102 assembly is completed.

In another example, the vehicle 102 may be part of a fleet of vehicles, and the test conditions 220 may instruct the vehicle 102 to send wiring diagnostic data 208 to the cable monitoring system 214 for testing of the fleet-specific timing conditions. For example, the fleet may specify test conditions 220 for the vehicle 102 to send wiring diagnostic data 208: one or more of at vehicle start-up, daily, weekly, monthly, after a predefined distance of travel, in response to a return of the vehicle 102 from a user, in response to an allocation of the vehicle 102 to a user, in response to one of the ECUs 104 of the vehicle 102 issuing a diagnostic code, etc. In one example, the test conditions 220 may be pushed to the vehicle 102 by a fleet operator.

In yet another example, the vehicle 102 may have user-defined test conditions 220 for the vehicle 102 to send the wiring diagnostic data 208: one or more of at vehicle start-up, daily, weekly, monthly, after a predefined distance traveled, in response to the occurrence of a DTC, and the like. In one example, these test conditions 220 may be applied to the vehicle 102 by the vehicle owner, for example, using the user's mobile device or using the HMI of the vehicle 102. In yet another example, the vehicle 102 may send the wiring diagnostic data 208 in response to receiving a request to do so, for example, from the cable monitoring system 214, from a user of the vehicle 102 or a mobile device of a fleet manager, or the like.

Fig. 5 illustrates an exemplary process 500 for the vehicle 102 to perform an on-board network diagnostic. In one example, in the context of system 200, process 500 may be performed by vehicle 102 in communication with cable monitoring system 214.

At operation 502, the vehicle 102 captures wiring diagnostic data 208. In one example, as described with respect to fig. 3-4, the vehicle 102 may capture cable diagnostic details 304, data transmission diagnostic details 306, and/or surrounding vehicle sensor readings 308, as described above.

At operation 504, the vehicle 102 determines whether the test condition 220 is satisfied. In one example, the test conditions 220 may specify one or more conditions that cause the vehicle 102 to transmit the captured wiring diagnostic data 208 to the cable monitoring system 214. For example, as described above, these conditions may include the vehicle 102 being in a factory mode, the vehicle 102 arriving at various stations during assembly, fleet-specific timing conditions of the vehicle 102, and/or user-defined test conditions 220 of the vehicle 102. If the test condition 220 is met, control passes to operation 506. Otherwise, control returns to operation 502.

At operation 506, the vehicle 102 transmits the cabling diagnostic data 208 to the cable monitoring system 214. In one example, the connectivity controller 104-I of the vehicle 102 may send the cabling diagnostic data 208 over the communication network 202 to the cloud server 204 hosting the cable monitoring service 214. Details of the on-board network diagnostics performed by cable monitoring service 214 are discussed in further detail with respect to process 600 in fig. 6.

At operation 508, the vehicle 102 receives the response from the cable monitoring system 214. In one example, the connectivity controller 104-I of the vehicle 102 may receive results of processing the cabling diagnostic data 208 from the cloud server 204 hosting the cable monitoring service 214 through the communication network 202.

At operation 510, the vehicle 102 determines whether any corrective actions 216 are indicated in the response to the vehicle 102. For example, in some examples, the cable monitoring system 214 may determine that the vehicle 102 is operating properly. In such cases, the cable monitoring system 214 may provide a response to the vehicle 102 (or to a device of the owner of the vehicle 102 or the fleet operator) indicating that the vehicle 102 is operating properly. In other examples, the response may include an indication that the vehicle 102 is in question. In this case, the response may also indicate one or more corrective actions 216 to be implemented by the vehicle 102. As described above, these corrective actions 216 may include an indication that the vehicle 102 is informed that service is sought, a new routing of the vehicle 102 data along a cleaner wiring segment within the vehicle 102 to avoid the segment with problems, and/or an update to the configuration of the vehicle 102 to reduce the data speed or reduce the update interval to otherwise adjust the data traffic to alleviate the problem of the segment with problems. If corrective action 216 is indicated, control passes to operation 512. Otherwise, control returns to operation 502.

After operation 512, the vehicle 102 applies the corrective action 216 to the vehicle 102. In one example, central gateway 110 and/or one or more ECUs 104 of the vehicle may implement corrective action 216. This may include, for example, changing the routing of signals along the vehicle bus 106, reducing data speed, or reducing update intervals while otherwise adjusting data traffic to alleviate problems, etc. After operation 512, control passes to operation 502.

Fig. 6 illustrates an exemplary process 600 for the cable monitoring system 214 to perform on-board network diagnostics. In one example, in the context of system 200, process 600 may be performed by cable monitoring system 214 in communication with vehicle 102.

At operation 602, the cable monitoring system 214 receives cabling diagnostic data 208 from the vehicle 102. In one example, cable monitoring system 214 receives cabling diagnostic data 208 over communication network 202 as discussed above with respect to operation 506 of process 500. The cable monitoring system 214 may store the cabling diagnostic data 208 to the cable monitoring data storage area 206 for processing.

At operation 604, the cable monitoring system 214 utilizes the trained machine learning model 210 to identify problems with the received cabling diagnostic data 208. In one example, the cable monitoring system 214 utilizes the machine learning model 210 to provide corrective actions to the vehicle 102 based on an analysis of the wiring diagnostic data 218 by the machine learning model 210. For example, the machine learning model 210 may utilize the wiring diagnostic data 218 to determine link quality and/or identify any outlier data points that may indicate problems with the wiring of the vehicle 102 based on the collected statistics of the other vehicles 102. The machine learning model 210 may be trained as described above and as described below with respect to process 700 in fig. 7.

At operation 606, if a problem is indicated, the cable monitoring system 214 passes control to operation 608 to send the corrective action 216 to the vehicle 102 at operation 608. In one example, cable monitoring system 214 sends corrective action 216 as discussed above with respect to operation 508 of process 500. If no problem is indicated, the cable monitoring system 214 may also optionally send a response indicating that no problem is indicated. In any event, after operation 608, or after determining that no problem is indicated, control passes to operation 602.

FIG. 7 illustrates an exemplary process 700 by which the cable monitoring system 214 retrains the machine learning model 210 to improve on-board network diagnostics. In one example, as with process 600, process 700 may be performed by cable monitoring system 214 in communication with vehicle 102 in the context of system 200.

At operation 702, the cable monitoring system 214 incorporates the received cabling diagnostic data 208 into the training data 212. The training data 212 may include wiring diagnostic data 208 labeled as indicating the link quality of the training data 212. Additionally, by having additional training data 212 from the active vehicle 102, the machine learning model 210 may be retrained to improve its performance over time. For example, in response to determining a problem with the vehicle 102, the cable monitoring service 214 may extract earlier wiring diagnostic data 218 from the vehicle 102 and tag that data as a likelihood of predicting a future problem before detecting the problem. By analyzing the characteristics of the vehicle 102 before the problem occurs, the cable monitoring service 214 may be able to provide predictions regarding expected maintenance problems or end-of-life for various wiring components. These predictions may be used to alert before a problem occurs and/or identify where changes are made to the design or assembly of the vehicle 102 to improve the life of the vehicle 102 components.

At operation 704, the cable monitoring system 214 retrains the machine learning model 210. For example, using training data 212 that incorporates received wiring diagnostic data 208, cable monitoring system 214 can adjust parameters in machine learning model 210, such as weights and biases, to allow machine learning model 210 to provide accurate results from tagged outputs in training data 212.

At operation 706, the cable monitoring system 214 applies the retrained machine learning model 210 for use. For example, the retrained machine learning model 210 may be used at operation 604 of the process 600 to improve the operation of the cable monitoring system 214. After operation 706, process 700 ends.

Thus, the disclosed method allows a technician to identify the exact wire segment that is problematic. This may allow for easy determination of the location of loose terminals or damaged cables or housings in case of sporadic problems. In addition, the disclosed methods may also provide the ability to predict and record the health of the vehicle bus 106 over time. In one enhancement, the system 200 may collect cable aging data based on predefined factors (such as changes over time due to thermal exposure), and may use this information to predict cable performance changes due to heat, electromagnetic compatibility, and the like.

Fig. 8 illustrates an exemplary computing device 802 for performing in-vehicle network diagnostics. Referring to fig. 8 and to fig. 1-7, ecu 104, central gateway 110, and cloud server 205 may be examples of such computing devices 802. The computing devices typically include computer-executable instructions, such as those in cable monitoring data storage area 206 and/or cable monitoring service 214, wherein the instructions are executable by one or more computing devices 802. Computer-executable instructions may be compiled or interpreted according to computer programs created using various programming languages and/or techniques, including, but not limited to, java, alone or in combination ^TM C, C ++, C#, visual Basic, javaScript, python, javaScript, perl, etc. Generally, a processor (e.g., a microprocessor) receives instructions, e.g., from a memory, a computer-readable medium, etc., and executes the instructions, thereby performing one or more processes, including one or more of the processes described herein. Such instructions and other data may be stored and transmitted using various computer-readable media, such as machine learning models 210, training data 212, corrective actions 216, wiring diagnostic data 218, and/or test conditions 220.

As shown, the computing device 802 may include a processor 804 operatively connected to a storage device 806, a network device 808, an output device 810, and an input device 812. It should be noted that this is merely an example, and that computing device 802 with more, fewer, or different components may be used.

The processor 804 may include one or more integrated circuits that implement the functionality of a Central Processing Unit (CPU) and/or a Graphics Processing Unit (GPU). In some examples, processor 804 is a system on a chip (SoC) that integrates the functions of a CPU and GPU. The SoC may optionally include other components (such as, for example, storage 806 and network 808) into a single integrated device. In other examples, the CPU and GPU are connected to each other via a peripheral connection device, such as a Peripheral Component Interconnect (PCI) express or another suitable peripheral data connection. In one example, the CPU is a commercially available central processing unit implementing one of a series of instruction sets, such as the x86, ARM, power, or microprocessor without interlocking pipeline stages (MIPS) instruction sets.

Regardless of the specifics, during operation, processor 804 executes stored program instructions that are retrieved from storage 806. The stored program instructions correspondingly include software that controls the operation of the processor 804 to carry out the operations described herein. The storage 806 may include both non-volatile memory and volatile memory devices. Nonvolatile memory includes solid state memory such as NAND (NAND) flash memory, magnetic and optical storage media, or any other suitable data storage device that retains data when the system is disabled or loses power. Volatile memory includes static and dynamic Random Access Memory (RAM) that stores program instructions and data during operation of the system 100.

The GPU may include hardware and software for displaying at least two-dimensional (2D) and optionally three-dimensional (3D) graphics to the output device 810. The output device 810 may include a graphical or visual display device, such as an electronic display screen, projector, printer, or any other suitable device that renders a graphical display. As another example, the output device 810 may include an audio device such as a speaker or headphones. As yet another example, the output device 810 may include a haptic device, such as a mechanically raisable device, which in an example may be configured to display braille or another physical output that may be touched to provide information to a user.

Input device 812 may include any of a variety of devices that enable computing device 802 to receive control inputs from a user. Examples of suitable input devices that receive human interface input may include a keyboard, mouse, trackball, touch screen, voice input device, tablet, and the like.

Network devices 808 may each include any of a variety of devices that enable the component to send and/or receive data from external devices over a network, such as communication network 202. Examples of suitable network devices 808 include an ethernet interface, a Wi-Fi transceiver, a cellular transceiver, or a bluetooth or Bluetooth Low Energy (BLE) transceiver, or other network adapter or peripheral interconnect device that receives data from another computer or external data storage device, which may be useful for receiving large amounts of data in an efficient manner.

With respect to the processes, systems, methods, heuristics, etc. described herein, it should be understood that, although the steps of such processes, etc. have been described as occurring according to some ordered sequence, such processes may be practiced with the described steps performed in an order different than that described herein. It should also be understood that certain steps may be performed concurrently, other steps may be added, or certain steps described herein may be omitted. In other words, the description of the processes herein is provided for the purpose of illustrating particular embodiments and should not be construed as limiting the claims in any way.

Accordingly, it is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and applications other than the examples provided will be apparent upon reading the above description. The scope should be determined not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. It is anticipated and intended that the technology discussed herein will evolve in the future, and that the disclosed systems and methods will be incorporated into such future embodiments. In summary, it should be understood that the present application is capable of modification and variation.

All terms used in the claims are intended to be given their broadest reasonable constructions and their ordinary meanings as understood by those skilled in the art described herein unless an explicit indication to the contrary is made herein. In particular, the use of singular articles such as "a," "an," "the," and the like are to be construed to recite one or more of the indicated elements unless a claim recites an explicit limitation to the contrary.

The Abstract of the disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. Furthermore, in the foregoing detailed description, it can be seen that various features are grouped together in various embodiments for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus the following claims are hereby incorporated into the detailed description, with each claim standing on its own as a separately claimed subject matter.

While exemplary embodiments are described above, these embodiments are not intended to describe all possible forms of the disclosure. Rather, the words used in the specification are words of description rather than limitation, and it is understood that various changes may be made without departing from the spirit and scope of the disclosure. Additionally, features of various implementing embodiments may be combined to form further embodiments of the disclosure.

According to the present invention, there is provided a system for performing on-vehicle network diagnosis, having: one or more cloud servers programmed to: receiving wiring diagnostic data from a vehicle, the wiring diagnostic data including information regarding electrical operation of a plurality of wiring segments of the vehicle; analyzing the wiring diagnostic data using a machine learning model; and responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, sending a response including one or more corrective actions to be performed by the vehicle to solve the problem.

According to one embodiment, the cabling diagnostic data includes cable diagnostic details of the plurality of cabling segments determined using Time Domain Reflectometry (TDR) functions of the vehicle integrated into a vehicle controller and/or inline with the plurality of cabling segments.

According to one embodiment, the cable diagnostic details include a link quality measured using the TDR function for each of the plurality of wire segments and a wire length for each of the plurality of wire segments.

According to one embodiment, the wiring diagnostic data includes data transmission diagnostic details specifying information about channel quality of data transmission along each of the plurality of wiring segments.

According to one embodiment, the wiring diagnostic data includes ambient vehicle sensor readings specifying information about one or more of temperature, weather, vehicle speed, vehicle acceleration, vehicle movement, date, or time of day.

According to one embodiment, the one or more corrective actions include an indication that the vehicle is seeking service.

According to one embodiment, the one or more corrective actions include a new routing of the vehicle data along the plurality of wire segments to be applied to the transmitted vehicle data to avoid a segment of the plurality of wire segments experiencing the problem.

According to one embodiment, the one or more corrective actions include updating a configuration of the vehicle to reduce data speed or change an update interval of data transmission along the plurality of segments to alleviate the problem.

According to one embodiment, the one or more cloud servers are further programmed to: retraining the machine learning model with predictive wiring diagnostic data received from a plurality of vehicles, the predictive wiring diagnostic data selected as wiring diagnostic data received from the plurality of vehicles prior to the plurality of vehicles encountering a problem, the predictive wiring diagnostic data being used to train the machine learning model to identify wiring diagnostic data that predicts a future problem; and analyzing additional wiring diagnostic data received from the vehicle using the retrained machine learning model.

According to one embodiment, the invention is further characterized by the vehicle comprising a central gateway in communication with a plurality of vehicle Electronic Control Units (ECUs) via one or more vehicle buses, the vehicle being programmed to transmit the wiring diagnostic data in response to the occurrence of a test condition maintained by the vehicle.

According to one embodiment, the one or more cloud servers are further programmed to send the test conditions to the vehicle.

According to one embodiment, the test conditions include the arrival of the vehicle at one or more intermediate assembly stations during assembly of the vehicle.

According to one embodiment, the test conditions include one or more of the following: the occurrence of a vehicle start, the occurrence of a predefined period of time, the response to a predefined distance traveled by the vehicle, the response to a change by a user of the vehicle, and/or the response to one of the plurality of ECUs of the vehicle.

According to the invention, a method for performing an on-board network diagnosis comprises: receiving wiring diagnostic data from a vehicle to a cloud system, the wiring diagnostic data including information regarding electrical operation of a plurality of wiring segments of the vehicle; analyzing the wiring diagnostic data using a machine learning model of the cloud system; and responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, sending a response including one or more corrective actions to be performed by the vehicle to solve the problem.

In one aspect of the invention, the wiring diagnostic data includes one or more of the following: cable diagnostic details of the plurality of wire segments determined using Time Domain Reflectometer (TDR) functions of the vehicle integrated into a vehicle controller and/or inline with the plurality of wire segments, the cable diagnostic details including a link quality measured using the TDR functions for each of the plurality of wire segments and a wire length for each of the plurality of wire segments; data transmission diagnostic details specifying information on channel quality of data transmission along each of the plurality of wire segments; or ambient vehicle sensor readings specifying information about one or more of temperature, weather, vehicle speed, vehicle acceleration, vehicle movement, date, or time of day.

In one aspect of the invention, the one or more corrective actions include one or more of: an indication that the vehicle is seeking service; vehicle data is selected along a new route within the vehicle to be applied to the plurality of wire segments of vehicle data to avoid a segment of the plurality of wire segments experiencing the problem; or an update to the configuration of the vehicle to reduce data speed or change the update interval of data transmission along the plurality of wire segments, thereby alleviating the problem.

In one aspect of the invention, the method comprises: retraining the machine learning model with predictive wiring diagnostic data received from a plurality of vehicles, the predictive wiring diagnostic data selected as wiring diagnostic data received from a vehicle prior to the vehicle encountering a problem, the predictive wiring diagnostic data being used to train the machine learning model to identify wiring diagnostic data that predicts a future vehicle problem; and analyzing additional wiring diagnostic data received from the vehicle using the retrained machine learning model.

In one aspect of the invention, the method comprises: transmitting test conditions from the cloud system to the vehicle; and receiving the wiring diagnostic data from the vehicle in response to the occurrence of the test condition.

In one aspect of the invention, the test conditions include one or more of the following: the vehicle reaching one or more intermediate assembly stations during vehicle assembly; or occurrence of a vehicle start, occurrence of a predefined period of time, occurrence of a diagnostic code in response to a predefined distance traveled by the vehicle, a change in a user of the vehicle, and/or in response to one of the plurality of ECUs of the vehicle.

According to the present invention, there is provided a non-transitory computer-readable medium having instructions for performing in-vehicle network diagnostics, which when executed by one or more cloud servers, cause the one or more cloud servers to perform operations comprising: receiving cabling diagnostic data from a vehicle, the cabling diagnostic data including information regarding electrical operation of a plurality of cabling segments of the vehicle, the cabling diagnostic data including cable diagnostic details of the plurality of cabling segments determined using Time Domain Reflectometry (TDR) functions of the vehicle integrated into a vehicle controller and/or inline with the plurality of cabling segments, the cable diagnostic details including link quality measured using the TDR functions for each of the plurality of cabling segments and cabling length for each of the plurality of cabling segments; analyzing the wiring diagnostic data using a machine learning model; and responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, sending a response including one or more corrective actions to be performed by the vehicle to solve the problem.

Claims

1. A system for performing on-board network diagnostics, comprising:

one or more cloud servers programmed to:

receiving wiring diagnostic data from a vehicle, the wiring diagnostic data including information regarding electrical operation of a plurality of wiring segments of the vehicle;

analyzing the wiring diagnostic data using a machine learning model; and

responsive to the machine learning model identifying a problem with the electrical operation based on the wiring diagnostic data, a response is sent that includes one or more corrective actions to be performed by the vehicle to solve the problem.

2. The system of claim 1, wherein the wiring diagnostic data includes cable diagnostic details of the plurality of wiring segments determined using a Time Domain Reflectometer (TDR) function of the vehicle integrated into a vehicle controller and/or inline with the plurality of wiring segments.

3. The system of claim 2, wherein the cable diagnostic details include a link quality measured using the TDR function for each of the plurality of wire segments and a wire length for each of the plurality of wire segments.

4. The system of claim 1, wherein the wiring diagnostic data includes data transmission diagnostic details specifying information about channel quality of data transmission along each of the plurality of wiring segments.

5. The system of claim 1, wherein the wiring diagnostic data includes ambient vehicle sensor readings specifying information about one or more of temperature, weather, vehicle speed, vehicle acceleration, vehicle movement, date, or time of day.

6. The system of claim 1, wherein the one or more corrective actions include an indication that the vehicle is seeking service.

7. The system of claim 1, wherein the one or more corrective actions include a new routing of vehicle data along the plurality of wire segments to be applied to the transmitted vehicle data to avoid a segment of the plurality of wire segments that is experiencing the problem.

8. The system of claim 1, wherein the one or more corrective actions include updating a configuration of the vehicle to reduce data speed or change an update interval of data transmission along the plurality of segments to alleviate the problem.

9. The system of claim 1, wherein the one or more cloud servers are further programmed to:

retraining the machine learning model with predictive wiring diagnostic data received from a plurality of vehicles, the predictive wiring diagnostic data selected as wiring diagnostic data received from the plurality of vehicles prior to the plurality of vehicles encountering a problem, the predictive wiring diagnostic data being used to train the machine learning model to identify wiring diagnostic data that predicts a future problem; and

Additional wiring diagnostic data received from the vehicle is analyzed using the retrained machine learning model.

10. The system of claim 1, further comprising the vehicle, wherein the vehicle comprises a central gateway in communication with a plurality of vehicle Electronic Control Units (ECUs) via one or more vehicle buses, the vehicle programmed to transmit the wiring diagnostic data in response to occurrence of a test condition maintained by the vehicle.

11. The system of claim 10, wherein the one or more cloud servers are further programmed to send the test conditions to the vehicle.

12. The system of claim 10, wherein the test condition comprises the vehicle reaching one or more intermediate assembly stations during vehicle assembly.

13. The system of claim 10, wherein the test conditions include one or more of: the occurrence of a vehicle start, the occurrence of a predefined period of time, the response to a predefined distance traveled by the vehicle, the response to a change by a user of the vehicle, and/or the response to one of the plurality of ECUs of the vehicle.

14. A method for performing on-board network diagnostics, comprising:

Receiving wiring diagnostic data from a vehicle to a cloud system, the wiring diagnostic data including information regarding electrical operation of a plurality of wiring segments of the vehicle;

analyzing the wiring diagnostic data using a machine learning model of the cloud system; and

15. The method of claim 14, wherein

The wiring diagnostic data includes one or more of:

cable diagnostic details of the plurality of wire segments determined using Time Domain Reflectometer (TDR) functions of the vehicle integrated into a vehicle controller and/or inline with the plurality of wire segments, the cable diagnostic details including a link quality measured using the TDR functions for each of the plurality of wire segments and a wire length for each of the plurality of wire segments;

data transmission diagnostic details specifying information on channel quality of data transmission along each of the plurality of wire segments; or (b)

Surrounding vehicle sensor readings specifying information about one or more of temperature, weather, vehicle speed, vehicle acceleration, vehicle movement, date, or time of day; or (b)

The one or more corrective actions include one or more of:

an indication that the vehicle is seeking service;

vehicle data is selected along a new route within the vehicle to be applied to the plurality of wire segments of vehicle data to avoid a segment of the plurality of wire segments experiencing the problem; or (b)

Updating the configuration of the vehicle to reduce data speed or change update intervals of data transmission along the plurality of wire segments, thereby alleviating the problem.